Ship power prediction and correction method, device and equipment based on neural network

Abstract

The invention discloses a ship power prediction and correction method, device and equipment based on a neural network, and relates to the technical field of ship power control, and the method comprises the steps: obtaining the historical navigation load power data of each ship on a target navigation line, selecting the target historical navigation load power data based on the energy consumption data, and constructing a training set; establishing a neural network prediction model for load power data prediction, and training the neural network prediction model by using the training set; predicting the predicted load power of the current shipping line position by adopting the trained neural network prediction model based on the current shipping line position of the ship; and correcting the load power output by the current ship in real time through the predicted load power obtained through prediction so as to control the power output of the current ship. According to the method, more targeted power output control can be adopted for specific driving scenes, and the driving experience is improved while energy is saved.

Description

Technical Field

[0001] The present application relates to the field of ship power control technology, and specifically to a method, device and equipment for predicting and correcting ship power based on a neural network. Background Art

[0002] A hybrid ship is one that is designed and built to use a propulsion method that is primarily powered by a combination of conventional gas or fuel powered engines and electrical sources. Hybrid ships are not fully electric, but coexist with conventional engines, so that for a given power demand, the supply comes from the engines as well as a supplement from battery sources. In addition, for some operations with low power requirements, such as berthing in port, loading and unloading at the terminal, or simply in standby mode, the power supply can be generated entirely by the batteries themselves.

[0003] With the continuous development of electric propulsion ships and hybrid ships, the requirements for their power systems are getting higher and higher. The short-term prediction of load power of hybrid ships is an important basis for the energy optimization management of their power systems and the optimal load power distribution between various power sources. Especially for ships with periodic operations, their load power between single working cycles has similar intrinsic characteristics. Fully understanding and mastering these inherent characteristics and achieving higher load power prediction accuracy will greatly affect the safety, stability and economy of ship operation. In order to meet the increasingly stringent requirements of energy conservation and emission reduction, it is imperative to vigorously develop hybrid ships. With the continuous advancement of electric power science and technology, hybrid technology is becoming more and more mature. Therefore, in the shipbuilding industry, as ships become more and more intelligent, the demand for precise control of ship power output is also increasing.

[0004] Currently, the control of ship power output is generally carried out by the driver based on experience, and it is impossible to adopt more targeted power output control for specific driving scenarios, which not only causes energy waste but also affects the driving experience. Summary of the invention

[0005] The present application provides a method, device and equipment for predicting and correcting ship power based on a neural network, which can adopt more targeted power output control for specific driving scenarios, thereby improving the driving experience while saving energy.

[0006] In a first aspect, an embodiment of the present application provides a ship power prediction and correction method based on a neural network, and the ship power prediction and correction method based on a neural network includes:

[0007] Obtain the historical navigation load power data of each ship on the target shipping line, and select the target historical navigation load power data based on the energy consumption data to construct a training set;

[0008] Establishing a neural network prediction model for load power data prediction, and using the training set to train the neural network prediction model;

[0009] Based on the current shipping line position of the ship, the trained neural network prediction model is used to predict the predicted load power at the current shipping line position;

[0010] The predicted load power obtained by prediction is used to correct the load power output of the current ship in real time to control the power output of the current ship.

[0011] In combination with the first aspect, in one implementation, the acquiring of historical navigation load power data of each ship on the target shipping line, and selecting target historical navigation load power data based on energy consumption data to construct a training set specifically includes:

[0012] Determine a target shipping line, and obtain historical navigation load power data of each ship on the target shipping line, wherein the historical navigation load power data includes the load power when the ship is located at a set position of each shipping line, and the energy consumption of the ship when completing the navigation of the target shipping line;

[0013] Based on the energy consumption from low to high, the ships are ranked, and the historical navigation load power data corresponding to a set number of ships are selected as the target historical navigation load power data to construct a training set.

[0014] In combination with the first aspect, in one implementation, the selecting of the historical navigation load power data corresponding to a set number of ships as the target historical navigation load power data to construct a training set specifically includes:

[0015] Obtain the load power of each target historical navigation load power data at each shipping line setting position, and obtain multiple load power values ​​for the same shipping line setting position;

[0016] The average of multiple load power values ​​obtained at the same shipping line setting position is calculated, and the average value is used as the load power value corresponding to the current shipping line setting position;

[0017] A training set is constructed based on the load power values ​​corresponding to the set positions of each shipping line.

[0018] In combination with the first aspect, in one implementation, based on the current shipping line position of the ship, the predicted load power at the current shipping line position is predicted using a trained neural network prediction model, specifically including:

[0019] Get the shipping line that the current ship is going to travel, and determine whether the obtained shipping line is the target shipping line:

[0020] If yes, based on the current position of the ship on the shipping line, the trained neural network prediction model is used to predict the predicted load power at the current position;

[0021] If not, the current position of the ship on the shipping line is obtained in real time, and when the ship reaches the set position of the shipping line, the load power of the ship at the current position is obtained and recorded.

[0022] In combination with the first aspect, in one implementation, the predicted load power obtained by prediction is used to correct the load power currently output by the ship in real time to control the power output of the current ship, specifically including:

[0023] Obtain the current real-time output load power of the ship and the predicted load power;

[0024] The difference between the predicted load power and the load power currently output by the ship in real time is calculated, and the output power of the ship is increased or decreased based on the difference to control the power output of the ship.

[0025] In combination with the first aspect, in one implementation, the current shipping line position of the ship is based on the confirmation of the current shipping line position of the ship, specifically:

[0026] When the shipping line is a river shipping line, a combination of image recognition technology and satellite positioning technology is used to determine the current shipping line position of the ship.

[0027] In combination with the first aspect, in one implementation, the method of combining image recognition technology and satellite positioning technology to determine the current shipping line position of the ship specifically includes:

[0028] Acquire image information around the ship based on the image sensor, and compare the acquired image information with the shipping line image information in the server to determine the current location of the ship;

[0029] Obtain the current location of the ship based on the satellite positioning sensor;

[0030] Compare the position obtained based on the image sensor with the position obtained based on the satellite positioning sensor:

[0031] If they are consistent, the confirmation of the ship's position is completed;

[0032] If there is any inconsistency, the ship's position will be confirmed based on active confirmation and the inconsistency will be recorded.

[0033] In a second aspect, an embodiment of the present application provides a ship power prediction and correction device based on a neural network, and the ship power prediction and correction device based on a neural network includes:

[0034] An acquisition module is used to acquire the historical navigation load power data of each ship on the target shipping line, and select the target historical navigation load power data based on the energy consumption data to construct a training set;

[0035] A construction module, which is used to establish a neural network prediction model for load power data prediction, and train the neural network prediction model using the training set;

[0036] A prediction module is used to predict the load power at the current shipping line position based on the current shipping line position of the ship using the trained neural network prediction model;

[0037] The correction module is used to correct the load power output of the current ship in real time by using the predicted load power obtained by prediction, so as to control the power output of the current ship.

[0038] In conjunction with the second aspect, in one implementation, the acquiring of historical navigation load power data of each ship on the target shipping line, and selecting target historical navigation load power data based on energy consumption data to construct a training set specifically includes:

[0039] Determine a target shipping line, and obtain historical navigation load power data of each ship on the target shipping line, wherein the historical navigation load power data includes the load power when the ship is located at a set position of each shipping line, and the energy consumption of the ship when completing the navigation of the target shipping line;

[0040] Based on the energy consumption from low to high, the ships are ranked, and the historical navigation load power data corresponding to a set number of ships are selected as the target historical navigation load power data to construct a training set.

[0041] In a third aspect, an embodiment of the present application provides a neural network-based ship power prediction and correction device, the neural network-based ship power prediction and correction device comprising a processor, a memory, and a neural network-based ship power prediction and correction program stored in the memory and executable by the processor, wherein when the neural network-based ship power prediction and correction program is executed by the processor, the steps of the above-mentioned neural network-based ship power prediction and correction method are implemented.

[0042] The beneficial effects brought by the technical solution provided by the embodiments of the present application include:

[0043] By acquiring the historical navigation load power data of each ship on the target shipping line, and selecting the target historical navigation load power data based on the energy consumption data, a training set is constructed, and then a neural network prediction model for load power data prediction is established, and the training set is used to train the neural network prediction model, and then based on the current shipping line position of the ship, the trained neural network prediction model is used to predict the predicted load power at the current shipping line position, and then the load power output of the current ship in real time is corrected by the predicted load power obtained by prediction to control the power output of the current ship, and an automatic identification method is adopted to automatically identify the load power of the current position of the ship through the neural network prediction model based on historical data, so as to correct the load power output of the ship, and adopt more targeted power output control for specific driving scenarios to save energy while improving driving experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a flow chart of the ship power prediction and correction method based on neural network in this application;

[0045] Figure 2 This is a schematic diagram of the functional modules of the neural network-based ship power prediction and correction device of the present application;

[0046] Figure 3 This is a schematic diagram of the hardware structure of the ship power prediction and correction device based on neural network in this application. DETAILED DESCRIPTION

[0047] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0048] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0049] On the first aspect, the embodiments of the present application provide a method for predicting and correcting ship power based on a neural network. The method adopts an automatic identification method and, based on historical data, automatically identifies the load power of the ship's current position through a neural network prediction model, thereby correcting the load power output of the ship and adopting more targeted power output control for specific driving scenarios, thereby saving energy and improving the driving experience.

[0050] In one embodiment, referring to Figure 1 , Figure 1 This is a flow chart of the ship power prediction and correction method based on neural network in this application. Figure 1 As shown, the ship power prediction and correction method based on neural network includes:

[0051] S1: Obtain the historical navigation load power data of each ship on the target shipping line, and select the target historical navigation load power data based on the energy consumption data to construct a training set;

[0052] Furthermore, in one embodiment, historical navigation load power data of each ship on the target shipping line is obtained, and target historical navigation load power data is selected based on energy consumption data to construct a training set, specifically including:

[0053] S101: Determine a target shipping line, and obtain historical navigation load power data of each ship on the target shipping line, wherein the historical navigation load power data includes the load power when the ship is located at a set position of each shipping line, and the energy consumption of the ship when completing the navigation of the target shipping line;

[0054] For example, if the power of ships passing through shipping line A needs to be corrected, then shipping line A is the target shipping line, and then the historical navigation load power data of each ship passing through shipping line A during the historical navigation process is obtained to obtain the energy consumption of each ship when completing shipping line A; at the same time, for shipping line A, multiple position points are selected as set positions to obtain the load power of each ship when passing through the set positions. The selection of the set position can be uniformly selected or actively selected based on the shipping line situation.

[0055] S102: Rank the ships in descending order based on their energy consumption, select the historical navigation load power data corresponding to a predetermined number of ships as target historical navigation load power data, and construct a training set.

[0056] For example, with respect to the energy consumption of each ship on shipping line A, the ships are ranked and the historical navigation load power data corresponding to the first set number of ships are selected as the target historical navigation load power data. In actual applications, the set number can be 10 or more to maintain the accuracy of subsequent predictions. For example, the historical navigation load power data of the first 10 ships are selected to construct a training set.

[0057] Furthermore, in one embodiment, historical navigation load power data corresponding to a predetermined number of ships are selected as target historical navigation load power data to construct a training set, specifically including:

[0058] S1021: Obtain the load power of each target historical navigation load power data at each set position of the shipping line, and obtain multiple load power values ​​for the same set position of the shipping line;

[0059] S1022: Calculate the average of multiple load power values ​​obtained at the same shipping line setting position, and use the average value as the load power value corresponding to the current shipping line setting position;

[0060] S1023: Construct a training set based on the load power value corresponding to the set position of each shipping line.

[0061] Specifically, for each selected target historical navigation load power data, each set position on the shipping line has a corresponding load power. Therefore, for the same set position on the target shipping line, multiple load powers can be obtained, and the average of the multiple load powers is calculated, and the average is used as the load power value corresponding to the current shipping line set position. Therefore, for each set position on the target shipping line, a corresponding load power value is obtained, so that a training set is constructed based on the load power value corresponding to each set position.

[0062] S2: Establishing a neural network prediction model for load power data prediction, and using the training set to train the neural network prediction model; by training the neural network prediction model, the trained neural network prediction model can obtain a load power value based on the position on the shipping line.

[0063] S3: Based on the current shipping line position of the ship, the trained neural network prediction model is used to predict the predicted load power at the current shipping line position;

[0064] Furthermore, in one embodiment, based on the current shipping line position of the ship, the predicted load power at the current shipping line position is predicted using the trained neural network prediction model, specifically including:

[0065] Get the shipping line that the current ship is going to travel, and determine whether the obtained shipping line is the target shipping line:

[0066] If yes, based on the current position of the ship on the shipping line, the trained neural network prediction model is used to predict the predicted load power at the current position;

[0067] If not, the current position of the ship on the shipping line is obtained in real time, and when it reaches the set position of the shipping line, the load power of the current ship at the current position is obtained and recorded as historical data to facilitate subsequent training of the neural network prediction model.

[0068] S4: The load power outputted by the current ship in real time is corrected by the predicted load power obtained by prediction, so as to control the power outputted by the current ship.

[0069] Furthermore, in one embodiment, the load power outputted by the current ship in real time is corrected by the predicted load power obtained by prediction to control the power outputted by the current ship, specifically including:

[0070] S401: Obtaining the current real-time output load power of the ship and the predicted load power;

[0071] S402: Calculate the difference between the predicted load power and the current real-time output load power of the ship, and increase or decrease the output power of the ship based on the difference to control the power output of the ship. For example, if the calculated predicted load power is greater than the current real-time output load power of the ship, the output power of the ship needs to be increased; if the calculated predicted load power is less than the current real-time output load power of the ship, the output power of the ship needs to be decreased.

[0072] It should be noted that in the process of correcting the power output of the ship, the predicted load power is only used as a reference. In actual situations, whether to adjust the ship's power data based on the predicted load power is decided by the driver based on the current actual driving conditions of the ship, with the premise of ensuring the safe operation of the ship.

[0073] Further, based on the current shipping line position of the ship, the confirmation of the current shipping line position of the ship is as follows:

[0074] When the shipping line is a river shipping line, a combination of image recognition technology and satellite positioning technology is used to determine the current shipping line position of the ship.

[0075] Furthermore, the current position of the ship on the shipping line is determined by combining image recognition technology and satellite positioning technology, including:

[0076] a: Obtain image information around the ship based on an image sensor, and compare the acquired image information with the shipping line image information in the server to determine the current location of the ship; the image sensor may be a camera;

[0077] b: Obtain the current location of the ship based on a satellite positioning sensor; the satellite positioning sensor may be a Beidou positioning device;

[0078] c: Compare the position obtained based on the image sensor with the position obtained based on the satellite positioning sensor:

[0079] If they are consistent, the confirmation of the ship's position is completed;

[0080] If there is any inconsistency, the ship's position will be confirmed based on active confirmation and the inconsistency will be recorded.

[0081] The neural network-based ship power prediction and correction method of the embodiment of the present application obtains the historical navigation load power data of each ship on the target shipping line, selects the target historical navigation load power data based on the energy consumption data, constructs a training set, and then establishes a neural network prediction model for load power data prediction, and uses the training set to train the neural network prediction model, and then based on the current shipping line position of the ship, the trained neural network prediction model is used to predict the predicted load power at the current shipping line position, and then the load power output of the current ship in real time is corrected by the predicted load power to control the power output of the current ship, and an automatic identification method is adopted to automatically identify the load power of the current position of the ship through the neural network prediction model based on historical data, so as to correct the load power output of the ship, and adopt a more targeted power output control for specific driving scenarios to save energy while improving the driving experience.

[0082] In a second aspect, an embodiment of the present application also provides a ship power prediction and correction device based on a neural network.

[0083] In one embodiment, referring to Figure 2 , Figure 2 This is a schematic diagram of the functional modules of the neural network-based ship power prediction and correction device of this application. Figure 2 As shown, the ship power prediction and correction device based on neural network includes: an acquisition module, a construction module, a prediction module, and a correction module.

[0084] The acquisition module is used to obtain the historical navigation load power data of each ship on the target shipping line, and select the target historical navigation load power data based on the energy consumption data to construct a training set; the construction module is used to establish a neural network prediction model for load power data prediction, and use the training set to train the neural network prediction model; the prediction module is used to predict the predicted load power at the current shipping line position based on the current shipping line position of the ship using the trained neural network prediction model; the correction module is used to correct the load power output of the current ship in real time by using the predicted load power obtained by prediction, so as to control the power output of the current ship.

[0085] In this application, the historical navigation load power data of each ship on the target shipping line is obtained, and the target historical navigation load power data is selected based on the energy consumption data to construct a training set, which specifically includes:

[0086] Determine a target shipping line, and obtain historical navigation load power data of each ship on the target shipping line, wherein the historical navigation load power data includes the load power when the ship is located at a set position of each shipping line, and the energy consumption of the ship when completing the navigation of the target shipping line;

[0087] Based on the energy consumption from low to high, the ships are ranked, and the historical navigation load power data corresponding to a set number of ships are selected as the target historical navigation load power data to construct a training set.

[0088] In this application, the historical navigation load power data corresponding to a set number of ships are selected as the target historical navigation load power data to construct a training set, which specifically includes:

[0089] Obtain the load power of each target historical navigation load power data at each set position of the shipping line, and obtain multiple load power values ​​for the same set position of the shipping line;

[0090] The average of multiple load power values ​​obtained at the same shipping line setting position is calculated, and the average value is used as the load power value corresponding to the current shipping line setting position;

[0091] A training set is constructed based on the load power values ​​corresponding to the set positions of each shipping line.

[0092] In this application, based on the current shipping line position of the ship, the trained neural network prediction model is used to predict the predicted load power at the current shipping line position, specifically including:

[0093] Get the shipping line that the current ship is going to travel, and determine whether the obtained shipping line is the target shipping line:

[0094] If yes, based on the current position of the ship on the shipping line, the trained neural network prediction model is used to predict the predicted load power at the current position;

[0095] If not, the current position of the ship on the shipping line is obtained in real time, and when the ship reaches the set position of the shipping line, the load power of the ship at the current position is obtained and recorded.

[0096] In this application, the load power outputted by the current ship in real time is corrected by the predicted load power obtained by prediction to control the power outputted by the current ship, specifically including:

[0097] Obtain the current real-time output load power of the ship and the predicted load power;

[0098] The difference between the predicted load power and the load power currently output by the ship in real time is calculated, and the output power of the ship is increased or decreased based on the difference to control the power output of the ship.

[0099] In this application, based on the current shipping line position of the ship, the confirmation of the current shipping line position of the ship is as follows:

[0100] When the shipping line is a river shipping line, a combination of image recognition technology and satellite positioning technology is used to determine the current shipping line position of the ship.

[0101] In this application, the image recognition technology and satellite positioning technology are combined to determine the current position of the ship on the shipping line, including:

[0102] Acquire image information around the ship based on the image sensor, and compare the acquired image information with the shipping line image information in the server to determine the current location of the ship;

[0103] Obtain the current location of the ship based on the satellite positioning sensor;

[0104] Compare the position obtained based on the image sensor with the position obtained based on the satellite positioning sensor:

[0105] If they are consistent, the confirmation of the ship's position is completed;

[0106] If there is any inconsistency, the ship's position will be confirmed based on active confirmation and the inconsistency will be recorded.

[0107] On the third aspect, an embodiment of the present application provides a ship power prediction and correction device based on a neural network. The ship power prediction and correction device based on a neural network can be a personal computer (PC), a laptop computer, a server, or other device with data processing capabilities.

[0108] Reference Figure 3 , Figure 3 The hardware structure diagram of the ship power prediction and correction device based on neural network involved in the embodiment of the present application is shown in FIG. In the embodiment of the present application, the ship power prediction and correction device based on neural network may include a processor, a memory, a communication interface and a communication bus.

[0109] The communication bus may be of any type and is used to interconnect the processor, the memory, and the communication interface.

[0110] The communication interface includes an input / output (I / O) interface, a physical interface, and a logical interface, etc., which are used to realize the interconnection of devices inside the ship power prediction and correction device based on a neural network, and an interface for realizing the interconnection of the ship power prediction and correction device based on a neural network with other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, an optical fiber interface, an ATM interface, etc.; the user device can be a display (Display), a keyboard (Keyboard), etc.

[0111] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0112] The processor may be a general-purpose processor, which may call the neural network-based ship power prediction and correction program stored in the memory, and execute the neural network-based ship power prediction and correction method provided in the embodiment of the present application. For example, the general-purpose processor may be a central processing unit (CPU). The method executed when the neural network-based ship power prediction and correction program is called may refer to the various embodiments of the neural network-based ship power prediction and correction method of the present application, which will not be repeated here.

[0113] Those skilled in the art will understand that Figure 3 The hardware structure shown in the figure does not constitute a limitation on the present application, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0114] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit "first", "second" and "third" to different types.

[0115] In the description of the embodiments of the present application, "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a specific way.

[0116] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; the “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.

[0117] In some processes described in the embodiments of the present application, multiple operations or steps that appear in a specific order are included, but it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present application or in parallel, and the sequence number of the operation is only used to distinguish the different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.

[0118] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present application.

[0119] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for predicting and correcting ship power based on neural network, characterized in that: The ship power prediction and correction method based on neural network includes: Obtain the historical navigation load power data of each ship on the target shipping line, and select the target historical navigation load power data based on the energy consumption data to construct a training set; Establishing a neural network prediction model for load power data prediction, and using the training set to train the neural network prediction model; Based on the current shipping line position of the ship, the trained neural network prediction model is used to predict the predicted load power at the current shipping line position; The predicted load power obtained by prediction is used to correct the load power output of the current ship in real time to control the power output of the current ship.

2. A method for predicting and correcting ship power based on a neural network as claimed in claim 1, characterized in that: The obtaining of historical navigation load power data of each ship on the target shipping line, and selecting target historical navigation load power data based on energy consumption data to construct a training set specifically includes: Determine a target shipping line, and obtain historical navigation load power data of each ship on the target shipping line, wherein the historical navigation load power data includes the load power when the ship is located at a set position of each shipping line, and the energy consumption of the ship when completing the navigation of the target shipping line; Based on the energy consumption from low to high, the ships are ranked, and the historical navigation load power data corresponding to a set number of ships are selected as the target historical navigation load power data to construct a training set.

3. A method for predicting and correcting ship power based on a neural network as claimed in claim 2, characterized in that: The selecting of the historical navigation load power data corresponding to the previously set number of ships as the target historical navigation load power data to construct a training set specifically includes: Obtain the load power of each target historical navigation load power data at each shipping line setting position, and obtain multiple load power values ​​for the same shipping line setting position; The average of multiple load power values ​​obtained at the same shipping line setting position is calculated, and the average value is used as the load power value corresponding to the current shipping line setting position; A training set is constructed based on the load power values ​​corresponding to the set positions of each shipping line.

4. A method for predicting and correcting ship power based on neural network as claimed in claim 1, characterized in that: The method of using the trained neural network prediction model to predict the load power at the current shipping line location based on the current shipping line location of the ship specifically includes: Get the shipping line that the current ship is going to travel, and determine whether the obtained shipping line is the target shipping line: If yes, based on the current position of the ship on the shipping line, the trained neural network prediction model is used to predict the predicted load power at the current position; If not, the current position of the ship on the shipping line is obtained in real time, and when the ship reaches the set position of the shipping line, the load power of the ship at the current position is obtained and recorded.

5. A method for predicting and correcting ship power based on neural network as claimed in claim 1, characterized in that: The predicted load power obtained by prediction is used to correct the load power outputted by the current ship in real time, so as to control the power outputted by the current ship, specifically including: Obtain the current real-time output load power of the ship and the predicted load power; The difference between the predicted load power and the load power currently output by the ship in real time is calculated, and the output power of the ship is increased or decreased based on the difference to control the power output of the ship.

6. A method for predicting and correcting ship power based on neural network as claimed in claim 1, characterized in that: The confirmation of the current shipping line position of the ship is based on the current shipping line position of the ship, specifically: When the shipping line is a river shipping line, a combination of image recognition technology and satellite positioning technology is used to determine the current shipping line position of the ship.

7. A method for predicting and correcting ship power based on a neural network as claimed in claim 6, characterized in that: The method of combining image recognition technology and satellite positioning technology to determine the current shipping line position of the ship specifically includes: Acquire image information around the ship based on the image sensor, and compare the acquired image information with the shipping line image information in the server to determine the current location of the ship; Obtain the current location of the ship based on the satellite positioning sensor; Compare the position obtained based on the image sensor with the position obtained based on the satellite positioning sensor: If they are consistent, the confirmation of the ship's position is completed; If there is any inconsistency, the ship's position will be confirmed based on active confirmation and the inconsistency will be recorded.

8. A ship power prediction and correction device based on neural network, characterized in that: The ship power prediction and correction device based on neural network includes: An acquisition module is used to acquire the historical navigation load power data of each ship on the target shipping line, and select the target historical navigation load power data based on the energy consumption data to construct a training set; A construction module, which is used to establish a neural network prediction model for load power data prediction, and train the neural network prediction model using the training set; A prediction module is used to predict the load power at the current shipping line position based on the current shipping line position of the ship using the trained neural network prediction model; The correction module is used to correct the load power output of the current ship in real time by using the predicted load power obtained by prediction, so as to control the power output of the current ship.

9. A ship power prediction and correction device based on neural network as claimed in claim 8, characterized in that: The obtaining of historical navigation load power data of each ship on the target shipping line, and selecting target historical navigation load power data based on energy consumption data to construct a training set specifically includes: Determine a target shipping line, and obtain historical navigation load power data of each ship on the target shipping line, wherein the historical navigation load power data includes the load power when the ship is located at a set position of each shipping line, and the energy consumption of the ship when completing the navigation of the target shipping line; Based on the energy consumption from low to high, the ships are ranked, and the historical navigation load power data corresponding to a set number of ships are selected as the target historical navigation load power data to construct a training set.

10. A ship power prediction and correction device based on neural network, characterized in that: The neural network-based ship power prediction and correction device includes a processor, a memory, and a neural network-based ship power prediction and correction program stored in the memory and executable by the processor, wherein when the neural network-based ship power prediction and correction program is executed by the processor, the steps of the neural network-based ship power prediction and correction method as described in any one of claims 1 to 7 are implemented.

Images